paper-with-me

홈 › Papers

AdaResNet: Enhancing Residual Networks with Dynamic Weight Adjustment for Improved Feature Integration

2024-08-19 · Hong Su

In very deep neural networks, gradients can become extremely small during backpropagation, making it challenging to train the early layers. ResNet (Residual Network) addresses this issue by enabling gradients to flow directly through the network via skip connections, facilitating the training of much deeper networks. However, in these skip connections, the input ipd is directly added to the transformed data tfd, treating ipd and tfd equally, without adapting to different scenarios. In this paper, we propose AdaResNet (Auto-Adapting Residual Network), which automatically adjusts the ratio between ipd and tfd based on the training data. We introduce a variable, weight}_{tfd}^{ipd, to represent this ratio. This variable is dynamically adjusted during backpropagation, allowing it to adapt to the training data rather than remaining fixed. Experimental results demonstrate that AdaResNet achieves a maximum accuracy improvement of over 50\% compared to traditional ResNet.

📄 PDF Abstract BibTeX arXiv:2408.09958

Code (1)

suguest/adaresnet 공식 구현 tf

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting

2026-04-20 · Hyeonseo Jang, Hyuk Kwon, Kibok Lee arxiv

We investigate recently introduced domain-class incremental learning scenarios for vision-language models (VLMs). Recent works address this challenge using parameter-efficient methods, such as prefix-tuning or adapters, …

Class Incremental LearningContinual Learning

Residual-Quantile Adjustment for Adaptive Training of Physics-informed Neural Network

2022-09-09 · Jiayue Han, Zhiqiang Cai, Zhiyou Wu, Xiang Zhou

Adaptive training methods for Physics-informed neural network (PINN) require dedicated constructions of the distribution of weights assigned at each training sample. To efficiently seek such an optimal weight distributio…

Adaptive boosting with dynamic weight adjustment

2024-06-01 · Vamsi Sai Ranga Sri Harsha Mangina

Adaptive Boosting with Dynamic Weight Adjustment is an enhancement of the traditional Adaptive boosting commonly known as AdaBoost, a powerful ensemble learning technique. Adaptive Boosting with Dynamic Weight Adjustment…

Ensemble Learning

Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

2023-07-08 · Liqi Xue, Tianyi Xu, Yongbao Song, Yan Liu 외

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic r…

Image Reconstructioninverse tone mappingInverse-Tone-MappingTone Mapping

RAMBA: 4D Radar Mapping by Bundle Adjustment

2026-05-24 · Jianzhu Huai, Yiwen Chen, Binliang Wang arxiv

4D radar is increasingly attractive for robotic mapping because it provides range, azimuth, elevation, and Doppler measurements while remaining robust in adverse visibility conditions. Although recent radar and radar--in…